Nova Lite

AmazonAmazonProprietary

描述

A low-cost multimodal model that is lightning fast for processing images, video, documents, and text.

发布日期

2024-12-03

参数规模

—

上下文长度

300K

支持模态

image, text, video

能力雷达图

general

coding

reasoning

science

agents

multimodal

排行榜排名

领域	#排名	分数	来源
代码能力榜	479	14.0	AA
通用能力榜	466	26.0	AA
科学能力	489	23.0	AA

基准测试分数 (LLM Stats)

(LLM Stats (zeroeval))

Agents

MM-Mind2Web

60.7%自报

Biology

GPQANYU + Cohere + Anthropic (2023)

42.0%自报

Code

HumanEvalOpenAI (2021)

85.4%自报

Economics

FinQA

73.6%自报

CRAG

43.8%自报

Finance

MMLU

80.5%自报

Frontend Development

VisualWebBench

77.7%自报

General

ARC-C

92.4%自报

IFEvalGoogle Research (2023)

89.7%自报

BFCL

66.6%自报

MMMU

56.2%自报

Grounding

GroundUI-1K

80.2%自报

Image To Text

DocVQADocVQA (2020)

92.4%自报

TextVQA

80.2%自报

Language

Translation Set1→en COMET22

88.8%自报

Translation en→Set1 COMET22

88.8%自报

BBH

82.4%自报

VATEX

77.8%自报

Translation Set1→en spBleu

43.1%自报

Translation en→Set1 spBleu

41.5%自报

SQuALITY

19.2%自报

Long Context

EgoSchema

71.4%自报

LVBench

40.4%自报

Math

GSM8k

94.5%自报

DROP

80.2%自报

MATH

73.3%自报

Multimodal

ChartQAMasry et al. (2022)

86.8%自报

AA 评测指数

(Artificial Analysis)

Math Index(Artificial Analysis)

7.0

Intelligence Index(Artificial Analysis)

6.7

Math 500(OpenAI (2024), subset of Hendrycks et al. MATH (2021))

0.8

Mmlu Pro(TIGER-Lab (Univ. of Waterloo, Toronto, CMU, 2024))

0.6

Gpqa(NYU + Cohere + Anthropic (2023))

0.4

Ifbench(Google Research (2023))

0.3

Lcr(Artificial Analysis)

0.2

Tau2(Sierra + U Toronto + Vector Institute (2025))

0.2

Livecodebench(UC Berkeley + MIT + Cornell (2024))

0.2

Scicode(UIUC + Argonne National Lab (2024))

0.1

Aime(MAA (Mathematical Association of America))

0.1

Aime 25(MAA (Mathematical Association of America))

0.1

Hle(Center for AI Safety + Scale AI (2025))

0.0

Terminalbench Hard(Stanford × Laude Institute (2026))

0.0

LLM Stats 分类评分

(LLM Stats (zeroeval))

Structured Output

Image To Text

Instruction Following

Code

Legal

Math

Multimodal

Reasoning

Finance

General

Healthcare

Tool Calling

Vision

Language

Frontend Development

Agents

Economics

Long Context

Physics

Biology

Chemistry

Summarization

定价

输入价格$0.06 / 1M tokens

输出价格$0.24 / 1M tokens

混合价格(3:1)$0.105 / 1M tokens

缓存读取价格$0.015 / 1M tokens

速度

Tokens/秒0.0

首Token延迟0.00s

首回答延迟0.00s

供应商价格排行

5 个供应商

最便宜: NanoGPT最贵: Amazon Bedrock

供应商输入输出

1NanoGPT最便宜

$0.0595

$0.238

2Amazon主要

$0.06

$0.24

3OpenRouter

$0.06

$0.24

4Kilo Gateway

$0.06

$0.24

5Amazon Bedrock

$0.06

$0.24

比较该模型在不同 API 供应商之间的定价。

外部链接

LLM Stats Artificial Analysis